Summary of Tender: Accelerating Large Language Models Via Tensor Decomposition and Runtime Requantization, by Jungi Lee et al.
Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization
by Jungi Lee, Wonbeom Lee, Jaewoong Sim
First submitted to arxiv on: 16 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Hardware Architecture (cs.AR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents an algorithm-hardware co-design solution called Tender, which enables efficient deployment of Large Language Model (LLM) inference at low precision. The authors propose a decomposed quantization technique that avoids explicit requantization when accumulating partial sums from decomposed matrices. This approach allows for higher accuracy and inference performance compared to state-of-the-art methods while minimizing intrusion into existing accelerators. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Tender is an algorithm-hardware co-design solution that makes large language models more efficient to deploy. It uses a special way of reducing the precision of calculations without losing too much accuracy. This helps make it faster and easier to use LLMs on computers and devices. |
Keywords
» Artificial intelligence » Inference » Large language model » Precision » Quantization
